AMDnet:An Academic Misconduct Detection Method for Authors’Behaviors

作     者：Shihao Zhou Ziyuan Xu JinHan Xingming Sun Yi Cao 

作者机构：Nanjing University of Information Science&TechnologyNanjing210044China Engineering Research Center of Digital ForensicsMinistry of EducationNanjing201144China Nanjing University(Suzhou)High and New Technology Research InstituteSuzhou215123China Jiangsu Union Technical InstituteWuxi214145China Department of Electrical and Computer EngineeringUniversity of WindsorONN9B 3P4Canada 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第71卷第6期

页      面：5995-6009页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：This work is supported by the National Key R&D Program of China under grant 2018YFB1003205 by the National Natural Science Foundation of China under grants U1836208 and U1836110 by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)fund and by the Collaborative Innovation Center of Atmospheric Environment and Equipment Technology(CICAEET)fund,China 

主　　题：Academic misconduct neural network imbalanced dataset 

摘      要：In recent years,academic misconduct has been frequently exposed by the media,with serious impacts on the academic *** research on academic misconduct focuses mainly on detecting plagiarism in article content through the application of character-based and non-text element detection techniques over the entirety of a *** the most part,these techniques can only detect cases of textual plagiarism,which means that potential culprits can easily avoid discovery through clever editing and alterations of text *** this paper,we propose an academic misconduct detection method based on scholars’submission *** model can effectively capture the atypical behavioral approach and operation of the *** such,it is able to detect various types of misconduct,thereby improving the accuracy of detection when combined with a text content *** model learns by forming a dual network group that processes text features and user behavior features to detect potential academic ***,the effect of scholars’behavioral features on the model are considered and ***,the Synthetic Minority Oversampling Technique(SMOTE)is applied to address the problem of imbalanced samples of positive and negative classes among contributing ***,the text features of the papers are combined with the scholars’behavioral data to improve recognition *** results on the imbalanced dataset demonstrate that our model has a highly satisfactory performance in terms of accuracy and recall.